In this paper, we study how to leverage calendar information to help with email re-finding using a zero-query prototype, Calendar-Aware Proactive Email Recommender System (CAPERS). CAPERS proactively selects and displays potentially useful emails to users based on their upcoming calendar events with a particular focus on meeting preparation. We approach this problem domain through a survey, a task-based experiment, and a field experiment comparing multiple email recommenders in a large technology company. We first show that a large proportion of email access is related to meetings and then study the effects of four email recommenders on user perception and engagement taking into account four categories of factors: the amount of email content, email recency, calendar-email content match, and calendar-email people match. We demonstrate that these factors all positively predict the usefulness of emails to meeting preparation and that calendar-email content match is the most important. We study the effects of different machine learning models for predicting usefulness and find that an online-learned linear model doubles user engagement compared with the baselines, which suggests the benefit of continuous online learning.

Query reformulation has been studied as a domain independent task. Existing work attempts to expand a query or substitute its terms with the same set of candidates regardless of the domain of this query. Since terms might be semantically related in one domain but not in others, it is more effective to provide candidates for queries with respect to their domain. This paper demonstrates the advantage of this domain dependent query reformulation approach, which learns its candidates, using a standard technique, for each domain from a separate sample of data derived automatically from a generic query log. Our results show that our approach statistically significantly outperforms the domain independent approach, which learns to reformulate from the same log using the same technique, on a large query set consisting of both health and commerce queries. Our results have very practical interpretation: while building different reformulation systems to handle queries from different domains does not require additional manual effort, it provides substantially better retrieval effectiveness than having a single system handling all queries. Additionally, we show that leveraging domain specific manually labelled data leads to further improvement.

We introduce a new relevance scoring technique that enhances existing relevance scoring schemes with term position information. This technique uses chronological term rank (CTR) which captures the positions of terms as they occur in the sequence of words in a document. CTR is both conceptually and computationally simple when compared to other approaches that use document structure information, such as term proximity, term order and document features. CTR works well when paired with Okapi BM25. We evaluate the performance of various combinations of CTR with Okapi BM25 in order to identify the most effective formula. We then compare the performance of the selected approach against the performance of existing methods such as Okapi BM25, pivoted length normalization and language models. Significant improvements are seen consistently across a variety of TREC data and topic sets, measured by the major retrieval performance metrics. This seems to be the first use of this statistic for relevance scoring. There is likely to be greater retrieval improvements possible using chronological term rank enhanced methods in future work.